preparing for data extraction

etl/xml_survey_extraction/XmlParser.py

@@ -44,8 +44,8 @@ def get_house_number(address: str) -> str | None:
 
 
 class XmlParser:
-    epc = None
-    additional_data = None
+    epc = {}
+    additional_data = {}
     uprn = None
 
     # heating/emissions information
@@ -72,12 +72,6 @@ class XmlParser:
 
     floor_dimensions = None
 
-    # The value of the URPN tells us about the file type that we're parsing
-    UPRN_FILETYPE_MAP = {
-        0: "EPR",
-        -1: "RDSAP_EPR"
-    }
-
     RATINGS_MAP = {
         "0": "N/A",
         "1": "Very Poor",
@@ -122,14 +116,11 @@ class XmlParser:
         self.filekey = filekey
         self.surveyor_company = surveyor_company
 
-        # The xml parser is use to parse the EPC and EPR xmls and different file types will contain different
-        # information
-        # In order to identify the file type, we can look for the presence of the 'UPRN' tag
-        # If the UPRN tag is present, we can assume that the file is an EPC
-        # If the UPRN tag is not present, we can assume that the file is an EPR
-        self.get_uprn(uprn)
+        # We check if we have a lig xml or rdsap xml
+        # We look for the presence of the Schema-Version-Original tag
+        self.is_lig = len(self.xml.getElementsByTagName("Schema-Version-Original")) > 0
 
-        self.file_type = self.UPRN_FILETYPE_MAP.get(self.uprn, "EPC")
+        self.get_uprn(uprn)
 
     @staticmethod
     def get_node(node):
@@ -145,10 +136,10 @@ class XmlParser:
         return node_first_child.nodeValue
 
     def run(self):
-        if self.file_type == "RDSAP_EPR":
-            # This file type contains just limited information compared to a regular EPR/EPC, and so we just exit
-            # unless we learn something else that determines that we need information from this file
+
+        if not self.is_lig:
             return
+
         self.get_assessor_details()
 
         self.get_heating_and_emissions_data()